© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 13914
    Prev
    Next
    INDEX
    Explanations

    words related to technology and product names

    oai_token-act-pair · gpt-3.5-turbo

    specific product names and technological terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     internationally
    -0.71
     arenas
    -0.70
     academic
    -0.70
     trademarks
    -0.70
     theological
    -0.70
     charitable
    -0.70
     lecture
    -0.69
     career
    -0.69
     analyst
    -0.69
     lavish
    -0.68
    POSITIVE LOGITS
    xit
    0.96
    Safe
    0.88
    ctuary
    0.88
    obal
    0.87
    ĸļ
    0.87
    Forward
    0.84
    Fax
    0.84
    Protect
    0.83
    É
    0.82
    keye
    0.82
    Activations Density 0.295%

    No Known Activations